Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Geng Hong

Geng Hong

5 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Crypto×5AI×3ML×1Info Retrieval×1

Frequent co-authors

Min Yang5×
Xudong Pan4×
Jiarun Dai3×
Yuan Zhang3×
Jiaqi Luo2×
Zhile Chen2×

Research Timeline

2026
Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

The paper introduces Tree structured Injection for Payloads (TIP), a novel black-box attack framework that reliably generates stealthy injection payloads to seize control of LLM agents utilizing the Model Context Protocol (MCP), even when defenses are present.

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

This paper systematically analyzes the resilience of LLM-enhanced search engines against black-hat SEO attacks, finding that while they block most traditional attacks, they remain vulnerable to sophisticated LLM-generated query manipulations.

AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent

AgentGuard is an attribute-based access control framework designed to mitigate severe security risks, such as privacy leakage and system compromise, in tool-using LLM-based agents.

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

The authors evaluate the autonomous penetration capabilities of 19 LLMs in a realistic cyberattack scenario.

AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges

The paper introduces AgentCyberRange, an open, multi-range infrastructure for measuring autonomous cyber attack capability in realistic cyber ranges, and evaluates six frontier AI systems.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.LGEmpiricalRecentJun 12, 2026

AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges

Fengyu Liu, Jiarun Dai, Yihe Fan, Wuyuao Mai +10 more

The paper introduces AgentCyberRange, an open, multi-range infrastructure for measuring autonomous cyber attack capability in realistic cyber ranges, and evaluates six frontier AI systems.

View →
cs.CRcs.AIEmpirical
Recent
Jun 11, 2026

The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems

Jiaqi Luo, Jiarun Dai, Zhile Chen, Jia Xu +7 more

The authors evaluate the autonomous penetration capabilities of 19 LLMs in a realistic cyberattack scenario.

View →
cs.CRRecentMay 27, 2026

AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent

Jiaqi Luo, Songyang Peng, Jiarun Dai, Zhile Chen +5 more

AgentGuard is an attribute-based access control framework designed to mitigate severe security risks, such as privacy leakage and system compromise, in tool-using LLM-based agents.

View →
cs.CRcs.IRMar 26, 2026

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

Pei Chen, Geng Hong, Xinyi Wu, Mengying Wu +5 more

This paper systematically analyzes the resilience of LLM-enhanced search engines against black-hat SEO attacks, finding that while they block most traditional attacks, they remain vulnerable to sophis…

View →
cs.CRcs.AIMar 25, 2026

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

Yulin Shen, Xudong Pan, Geng Hong, Min Yang

The paper introduces Tree structured Injection for Payloads (TIP), a novel black-box attack framework that reliably generates stealthy injection payloads to seize control of LLM agents utilizing the M…

View →